The AI set up his hallway lights and motion routine from a plain description
The AI set up a complex Home Assistant routine with lights and motion sensors from a description, working when he walks past the sensor.
A random mix from the whole library. Shuffle for a new set.
The AI set up a complex Home Assistant routine with lights and motion sensors from a description, working when he walks past the sensor.
He set the AI Tasks up to look up Berkeley housing updates on its own and match what it finds against his own tracker. He called it scary, but useful.
He set up saved searches on Cars.com, Carvana and CarMax with his makes, models, price, year and features, and favorited cars on each. The AI merged them into one list, checked price guidance, mileage, consumer reports, recalls and reliability, named his ten best and ten worst, and removed the bottom ten from his favorites. They repeated the rounds until the list was tight, then refined by color and features. He test drove two cars from the list. While he was out, the AI checked the stock of two dealerships he drove past, just from him naming the brands nearby, and found one more match. Every morning it reruns the searches, removing cars that sold and adding new ones.
He bought an M5Stack stopwatch for 45 euros and never used it as one. With the AI he turned it into a round Home Assistant info display with 14 modules overnight, in under 25 minutes of typing himself.
During a week-long, move-in agent test, the journalist's the AI (Mark) logged into her Facebook, scoured Marketplace for couches, lamps and rugs, drafted and sent seller messages with her approval, and managed the replies. The hunt ended with a real purchase: an AI-sourced dining table.
In the same week as his treadmill buy, a SpaceX launch engineer says his AI got several quotes for new car tires, paid for them, and scheduled the install. No prices or shop names were shown.
He runs the AI on his PC with ha-mcp on the same machine, so the AI can reach into Home Assistant and make the changes he asks for. He keeps it on his own PC only, and says a new dashboard is done as soon as he describes it.
Got the AI to implement TPAP compatibility in Swift purely by interacting with his local plugs and response shapes plus RFC 9383, figuring out it was SPAKE2+ and the password hashing steps.
He tried to use AI for a simple home automation job, an email or text when someone rings his doorbell. He calls it a complete failure.
A commenter in a hardware reverse-engineering thread says he had the AI develop a working Bluetooth CUPS driver for his Canon Zoemini 2 mini photo printer. Canon only supports the printer from smartphones, so the driver made it usable from his Linux machine.
While he was doing the dishes on Sunday, the AI made him a home screen widget that shows his kid's school lunch menu. He says he never would have made it himself.
A hobbyist says the AI assembled the firmware running his living-room lights and fans: an ESP32 web server driving a radio transmitter. It also built him a Streamlit app to explore the signals, and the code is public on GitHub.
His 2019 LG TV has a great screen, but the official Plex app took about 30 seconds just to show the profile picker, because it is really a web page. There is no public native toolkit for the TV, so he rooted a spare set, read the TVs own software with analysis tools and the AI, and built a native Plex client of his own. On the same TV it shows the profile picker in about 3 seconds.
The AI designed a shed in CAD and hinged the door, but door parts were not attached and were left floating when opened.
A dad with no building experience spent a weekend with AI and an $89 circuit board and made his son a talking dinosaur toy. It reads stories, plays the radio, and tells jokes, and it works.
The AI and the AI re-created a Tesla data tool in Go from an existing codebase at his request; he has used the new tool for 5 months and it works well.
MindStudio tested an AI monitor that watches Autotrader listings and flags cars priced well under market. Scheduled checks deliver deal alerts to Telegram, and a continuity setting stops it re-alerting on the same listing.
The AI sold the user's car end to end: listing it, handling buyers, collecting CarMax and Carvana quotes, and preparing the licensing paperwork.
The third case in the same comment: he had the AI call three local companies to get quotes for a fence at his property. Quote gathering for home work normally means three rounds of calls, messages and waiting; his agent made the calls itself. Prices are not stated in the comment.
He sent the AI a photo of a clock, it worked out what non-standard battery it took and ordered it from Amazon for him.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.